Velocity-History-Based Soft Actor-Critic Tackling IROS'24 Competition "AI Olympics with RealAIGym"

The ``AI Olympics with RealAIGym'' competition challenges participants to stabilize chaotic underactuated dynamical systems with advanced control algorithms. In this paper, we present a novel solution submitted to IROS'24 competition, which builds upon Soft Actor-Critic (SAC), a popular model-free entropy-regularized Reinforcement Learning (RL) algorithm. We add a `context' vector to the state, which encodes the immediate history via a Convolutional Neural Network (CNN) to counteract the unmodeled effects on the real system. Our method achieves high performance scores and competitive robustness scores on both tracks of the competition: Pendubot and Acrobot.

Beyond the Cascade: Juggling Vanilla Siteswap Patterns

Being widespread in human motor behavior, dynamic movements demonstrate higher efficiency and greater capacity to address a broader range of skill domains compared to their quasi-static counterparts. Among the frequently studied dynamic manipulation problems, robotic juggling tasks stand out due to their inherent ability to scale their difficulty levels to arbitrary extents, making them an excellent subject for investigation. In this study, we explore juggling patterns with mixed throw heights, following the vanilla siteswap juggling notation, which jugglers widely adopted to describe toss juggling patterns. This requires extending our previous analysis of the simpler cascade juggling task by a throw-height sequence planner and further constraints on the end effector trajectory. These are not necessary for cascade patterns but are vital to achieving patterns with mixed throw heights. Using a simulated environment, we demonstrate successful juggling of most common 3-9 ball siteswap patterns up to 9 ball height, transitions between these patterns, and random sequences covering all possible vanilla siteswap patterns with throws between 2 and 9 ball height. https://kai-ploeger.com/beyond-cascades

Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation

Learning skills that interact with objects is of major importance for robotic manipulation. These skills can indeed serve as an efficient prior for solving various manipulation tasks. We propose a novel Skill Learning approach that discovers composable behaviors by solving a large and diverse number of autonomously generated tasks. Our method learns skills allowing the robot to consistently and robustly interact with objects in its environment. The discovered behaviors are embedded in primitives which can be composed with Hierarchical Reinforcement Learning to solve unseen manipulation tasks. In particular, we leverage Asymmetric Self-Play to discover behaviors and Multiplicative Compositional Policies to embed them. We compare our method to Skill Learning baselines and find that our skills are more interactive. Furthermore, the learned skills can be used to solve a set of unseen manipulation tasks, in simulation as well as on a real robotic platform.

Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability

Optimal decision-making under partial observability requires reasoning about the uncertainty of the environment's hidden state. However, most reinforcement learning architectures handle partial observability with sequence models that have no internal mechanism to incorporate uncertainty in their hidden state representation, such as recurrent neural networks, deterministic state-space models and transformers. Inspired by advances in probabilistic world models for reinforcement learning, we propose a standalone Kalman filter layer that performs closed-form Gaussian inference in linear state-space models and train it end-to-end within a model-free architecture to maximize returns. Similar to efficient linear recurrent layers, the Kalman filter layer processes sequential data using a parallel scan, which scales logarithmically with the sequence length. By design, Kalman filter layers are a drop-in replacement for other recurrent layers in standard model-free architectures, but importantly they include an explicit mechanism for probabilistic filtering of the latent state representation. Experiments in a wide variety of tasks with partial observability show that Kalman filter layers excel in problems where uncertainty reasoning is key for decision-making, outperforming other stateful models.

Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning

Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. While most approaches in the Safe Reinforcement Learning area do not require prior knowledge of constraints and robot kinematics and rely solely on data, it is often difficult to deploy them in complex real-world settings. Instead, model-based approaches that incorporate prior knowledge of the constraints and dynamics into the learning framework have proven capable of deploying the learning algorithm directly on the real robot. Unfortunately, while an approximated model of the robot dynamics is often available, the safety constraints are task-specific and hard to obtain: they may be too complicated to encode analytically, too expensive to compute, or it may be difficult to envision a priori the long-term safety requirements. In this paper, we bridge this gap by extending the safe exploration method, ATACOM, with learnable constraints, with a particular focus on ensuring long-term safety and handling of uncertainty. Our approach is competitive or superior to state-of-the-art methods in final performance while maintaining safer behavior during training.

One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion

Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world.

Adaptive Control based Friction Estimation for Tracking Control of Robot Manipulators

Adaptive control is often used for friction compensation in trajectory tracking tasks because it does not require torque sensors. However, it has some drawbacks: first, the most common certainty-equivalence adaptive control design is based on linearized parameterization of the friction model, therefore nonlinear effects, including the stiction and Stribeck effect, are usually omitted. Second, the adaptive control-based estimation can be biased due to non-zero steady-state error. Third, neglecting unknown model mismatch could result in non-robust estimation. This paper proposes a novel linear parameterized friction model capturing the nonlinear static friction phenomenon. Subsequently, an adaptive control-based friction estimator is proposed to reduce the bias during estimation based on backstepping. Finally, we propose an algorithm to generate excitation for robust estimation. Using a KUKA iiwa 14, we conducted trajectory tracking experiments to evaluate the estimated friction model, including random Fourier and drawing trajectories, showing the effectiveness of our methodology in different control schemes.

ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching

Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex manipulation tasks, the absence of a representation that encodes intricate spatial relationships between observations and actions often limits spatial generalization, necessitating large amounts of demonstrations. To tackle this problem, we introduce a novel policy class, ActionFlow. ActionFlow integrates spatial symmetry inductive biases while generating expressive action sequences. On the representation level, ActionFlow introduces an SE(3) Invariant Transformer architecture, which enables informed spatial reasoning based on the relative SE(3) poses between observations and actions. For action generation, ActionFlow leverages Flow Matching, a state-of-the-art deep generative model known for generating high-quality samples with fast inference - an essential property for feedback control. In combination, ActionFlow policies exhibit strong spatial and locality biases and SE(3)-equivariant action generation. Our experiments demonstrate the effectiveness of ActionFlow and its two main components on several simulated and real-world robotic manipulation tasks and confirm that we can obtain equivariant, accurate, and efficient policies with spatially symmetric flow matching. Project website: https://flowbasedpolicies.github.io/

Safe and Efficient Path Planning under Uncertainty via Deep Collision Probability Fields

Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning. This is an important building block of modern planning algorithms in many application scenarios such as autonomous driving, where noisy sensors perceive obstacles. While many approaches exist, they either provide too conservative estimates of the collision probabilities or are computationally intensive due to their sampling-based nature. To deal with these issues, we introduce Deep Collision Probability Fields, a neural-based approach for computing collision probabilities of arbitrary objects with arbitrary unimodal uncertainty distributions. Our approach relegates the computationally intensive estimation of collision probabilities via sampling at the training step, allowing for fast neural network inference of the constraints during planning. In extensive experiments, we show that Deep Collision Probability Fields can produce reasonably accurate collision probabilities (up to 10^{-3}) for planning and that our approach can be easily plugged into standard path planning approaches to plan safe paths on 2-D maps containing uncertain static and dynamic obstacles. Additional material, code, and videos are available at https://sites.google.com/view/ral-dcpf.

Inverse decision-making using neural amortized Bayesian actors

Bayesian observer and actor models have provided normative explanations for many behavioral phenomena in perception, sensorimotor control, and other areas of cognitive science and neuroscience. They attribute behavioral variability and biases to different interpretable entities such as perceptual and motor uncertainty, prior beliefs, and behavioral costs. However, when extending these models to more complex tasks with continuous actions, solving the Bayesian decision-making problem is often analytically intractable. Moreover, inverting such models to perform inference over their parameters given behavioral data is computationally even more difficult. Therefore, researchers typically constrain their models to easily tractable components, such as Gaussian distributions or quadratic cost functions, or resort to numerical methods. To overcome these limitations, we amortize the Bayesian actor using a neural network trained on a wide range of different parameter settings in an unsupervised fashion. Using the pre-trained neural network enables performing gradient-based Bayesian inference of the Bayesian actor model's parameters. We show on synthetic data that the inferred posterior distributions are in close alignment with those obtained using analytical solutions where they exist. Where no analytical solution is available, we recover posterior distributions close to the ground truth. We then show that identifiability problems between priors and costs can arise in more complex cost functions. Finally, we apply our method to empirical data and show that it explains systematic individual differences of behavioral patterns.